INDEX

Explanations

terms related to legislative and policy discussions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.16

akens

-0.16

 misunder

-0.15

 nÃ¤ch

-0.15

elves

-0.15

zew

-0.14

.scalablytyped

-0.14

 EXEMPLARY

-0.14

UV

-0.14

dre

-0.14

POSITIVE LOGITS

0.26

'(

0.19

,(

0.19

(.

0.18

 download

0.17

arget

0.16

()(

0.16

'.

0.16

&apos

0.16

uploaded

0.16

Activations Density 0.057%

terms related to legislative and policy discussions

No Comments

No Known Activations